A pseudo point identification method, a terminal device and a computer readable storage medium

Abstract

The application discloses a pseudo point identification method, a terminal device and a computer readable storage medium, and belongs to the technical field of laser radar, and comprises the following steps: slidingly traversing each point in point cloud data returned by a radar to determine a data analysis area of each point; determining a statistical result of points in the data analysis area that meet a preset statistical condition according to a distance difference value of each point; and identifying pseudo points in the point cloud data based on the statistical result, so that the pseudo points in the point cloud data can be effectively identified, and the problem that the pseudo points in the point cloud data cannot be effectively identified at present can be solved.

Description

Technical Field

[0001] This application belongs to the field of lidar technology, and particularly relates to a method for artifact point identification, a terminal device, and a computer-readable storage medium. Background Technology

[0002] Due to its advantages such as high resolution, high sensitivity, strong anti-interference ability, and unaffected by dark conditions, lidar is often used in fields such as autonomous driving, logistics vehicles, robots, and intelligent public transportation.

[0003] Because the beam of a lidar is non-rational and its spot has a certain area, when two target objects are close to each other in the same direction, the beam will produce two echoes when it hits the boundary between the two objects. Since the two target objects are close to each other, there will be an aliasing effect between the two echoes, which will cause artifacts to appear in the received point cloud image at the position between the two target objects, i.e., the dragging phenomenon. The existence of the dragging phenomenon will cause the distance measurement of the target objects to be incorrect.

[0004] However, existing technologies have the problem of not being able to effectively identify whether point cloud data is real objects or dragged-out artifacts. Invention Overview

[0006] Technical issues

[0007] In view of this, embodiments of this application provide a method for identifying artifact points, a terminal device, and a computer-readable storage medium to solve the problem in the prior art that it is impossible to effectively identify whether point cloud data is a real object or a dragging artifact point.

[0008] Solution to the problem

[0009] Technical solutions

[0010] In a first aspect, embodiments of this application provide a method for artifact point recognition, including:

[0011] A sliding traversal is performed on each point in the point cloud data transmitted back by the radar to determine the data analysis area for each point;

[0012] The statistical results of points in the data analysis area that meet the preset statistical conditions are determined based on the distance difference value of each point;

[0013] Based on the statistical results, artifact points in the point cloud data are identified.

[0014] In one implementation of the first aspect, before determining the statistical results of points in the data analysis region that satisfy preset statistical conditions based on the distance difference value of each point, the method further includes:

[0015] Calculate the distance difference value for each point in the data analysis area.

[0016] In one implementation of the first aspect, determining the statistical results of points in the data analysis area that satisfy preset statistical conditions based on the distance difference value of each point includes:

[0017] Points in the data analysis area with a distance difference greater than a specific threshold are weighted and recorded as the first statistical result;

[0018] The number of consecutive points based on the coordinates of each point in the first statistical result is counted and recorded as the second statistical result;

[0019] Based on the difference distance values ​​of each point in the first statistical result, count the number of points whose distance increased and the number of points whose distance decreased, and record them as the third statistical result and the fourth statistical result, respectively.

[0020] Based on the difference distance values ​​of each point in the first statistical result, count the number of points where the distance difference between two consecutive points is not equal or does not satisfy the geometric relationship, and record it as the fifth statistical result;

[0021] If the distance difference between the first and last points of the data analysis area is greater than the first preset threshold and less than the second preset threshold, then the variable identifier will be set.

[0022] In one implementation of the first aspect, identifying artifact points in the point cloud data based on the statistical results includes:

[0023] Set recognition conditions based on recognition accuracy;

[0024] Based on the identification conditions, the statistical results are judged to determine the artifact points in the point cloud data.

[0025] In one implementation of the first aspect, if the first statistical result is greater than the first statistical threshold, the second statistical result is greater than the second statistical threshold, the fifth statistical result is greater than the third statistical threshold, the variable identifier is set, and the distance difference monotonically increases or decreases, then the center point of the data analysis area is determined to be an artifact point.

[0026] In one implementation of the first aspect, if the first statistical result is greater than the first statistical threshold, the second statistical result is greater than the second statistical threshold, the fifth statistical result is greater than the third statistical threshold, the variable identifier is set, the third statistical result or the fourth statistical result is less than or equal to the fourth statistical threshold, and the point before the current point is an artifact point, then the center point of the data analysis area is determined to be an artifact point.

[0027] In one implementation of the first aspect, the artifact point recognition method further includes:

[0028] Remove the artifact points from the point cloud data.

[0029] Secondly, embodiments of this application provide a terminal device, including:

[0030] The determination unit is used to perform a sliding traversal of each point in the point cloud data returned by the radar to determine the data analysis area of ​​each point;

[0031] The statistical unit is used to determine the statistical results of points in the data analysis area that meet preset statistical conditions based on the distance difference value of each point;

[0032] The identification unit is used to identify artifact points in the point cloud data based on the statistical results.

[0033] Thirdly, embodiments of this application provide a terminal device, the terminal device including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method as described in the first aspect or any optional manner of the first aspect.

[0034] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method as described in the first aspect or any optional manner of the first aspect.

[0035] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute the method described in the first aspect or any optional manner of the first aspect.

[0036] Beneficial effects of the invention

[0037] Beneficial effects

[0038] The artifact point recognition method, terminal device, computer-readable storage medium, and computer program product provided in this application have the following beneficial effects:

[0039] By sliding through each point in the point cloud data, statistical results of points that meet preset statistical conditions are obtained based on the distance difference results of the point cloud. Then, based on the statistical results, artifact points in the point cloud data are accurately identified, which can effectively identify artifact points in point cloud data and solve the current problem of not being able to effectively identify artifact points in point cloud data.

[0040] Brief description of the accompanying drawings Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic diagram of a scene where a radar-emitted light spot hits the boundary between two objects, as provided in an embodiment of this application.

[0043] Figure 2 This is a schematic diagram of the echo when the radar beam emitted by the radar hits the boundary between two objects, as provided in the embodiments of this application.

[0044] Figure 3 This is a schematic flowchart illustrating an artifact point recognition method provided in an embodiment of this application.

[0045] Figure 4 This is a schematic diagram of the implementation process of S12 provided in the embodiments of this application;

[0046] Figure 5 This is a schematic diagram of the artifact points formed by the dragging phenomenon provided in the embodiments of this application;

[0047] Figure 6 This is a comparison image of a point cloud image containing artifact points provided in the embodiments of this application and a point cloud image after artifact points have been removed by the artifact point recognition method provided in the embodiments of this application.

[0048] Figure 7 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application;

[0049] Figure 8 This is a schematic diagram of the structure of a terminal device provided in another embodiment of this application;

[0050] Figure 9 This is a schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of this application.

[0051] Invention Embodiments

[0052] Embodiments of the present invention

[0053] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0054] It should be understood that the term "and / or" as used in this application specification and the appended claims refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes such combinations. Furthermore, in the description of this application specification and the appended claims, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0055] It should also be understood that references to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include the specific features, structures, or characteristics described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0056] A lidar (Light Detection and Ranging) system is an automated remote sensing device that uses a laser as its emission source and employs photoelectric detection technology for detection. A lidar system can include a transmitting system, a receiving system, a scanning control system, and a data processing system. The working principle of lidar is that it emits a detection signal towards a target object. After the signal hits the target object, the object reflects the signal, forming an echo signal. The receiving system receives and processes this echo signal to obtain information such as the target object's distance, size, speed, and reflectivity.

[0057] Please see Figure 1 When two target objects (target object 1 and target object 2) are located close to each other in the same direction, the laser beam emitted by the lidar will produce two echoes when it hits the boundary between the two objects. For example... Figure 2 As shown, after the light spot hits target object 1 and target object 2, reflections occur at times T1 and T2 respectively. Due to the resolution limitation of the receiving system, the two received echoes will overlap into a wide beam echo, and its echo time will be estimated as time T3, which will lead to ranging errors.

[0058] Currently, it is not possible to effectively identify artifact points in point cloud data. If artifact points are not processed, false point clouds (artifact points) will lead to the formation of false target objects, resulting in ranging errors. If artifact points are excessively removed, real slope objects will be misjudged, which will also affect the ranging results.

[0059] To address the aforementioned shortcomings, this application embodiment employs a sliding traversal of each point in the point cloud data. Based on the distance difference results of the point cloud, it statistically analyzes the points that meet preset statistical conditions. Then, based on these statistical results, it accurately identifies artifact points in the point cloud data. This effectively identifies artifact points in point cloud data, solving the current problem of the inability to effectively identify artifact points in point cloud data. The artifact point identification method provided by this application embodiment will be described in detail below:

[0060] Please see Figure 3 , Figure 3 This is a schematic flowchart illustrating an artifact point recognition method provided in this application embodiment. The execution entity of the artifact point recognition method provided in this application embodiment is a terminal device communicatively connected to a LiDAR. This terminal device can be a mobile terminal such as a smartphone, tablet, or wearable device, or it can be a computer, cloud server, radar-assisted computer, etc., in various application scenarios. It should be noted that the artifact point recognition method provided in this application embodiment is applicable to any form of LiDAR product, including but not limited to mechanical LiDAR, MEMS LiDAR, FLASH LiDAR, OPA LiDAR, etc.

[0061] like Figure 3 As shown, the artifact point recognition method provided in this application embodiment may include S11~S13, which are detailed below:

[0062] S11: Perform a sliding traversal on each point in the point cloud data returned by the radar to determine the data analysis area for each point.

[0063] In this embodiment of the application, the terminal device acquires point cloud data uploaded by the radar, and then performs a sliding traversal of each point in the point cloud data to identify each point.

[0064] In one implementation, after receiving the echo, the radar system can upload the received data to a connected terminal device, which then analyzes the point cloud data. In another optional embodiment, after receiving the echo, the radar system can transmit the received data to a radar data processing module, process the data, and then output the processed data. It is understood that the data processing module can be integrated into the radar control system.

[0065] In this embodiment, the data analysis area can be determined based on horizontal and / or vertical neighborhoods. A horizontal neighborhood refers to a data analysis area defined horizontally with the current point as its center. For example, if the current data is in the first row and the radius of the data analysis area is determined to be L / 2, then the horizontal neighborhood of the data analysis can be a region of 1 row and L columns. A vertical neighborhood refers to a data analysis area defined vertically with the current point as its center. For example, if the current data is in the first column and the radius of the data analysis area is determined to be L / 2, then the vertical neighborhood of the data analysis can be a region of L rows and 1 column, where L is a positive integer greater than 1. The radii of the horizontal and vertical analysis areas can be the same or different, without restriction.

[0066] For example, assuming the current point's coordinates are (m, n), the data analysis region is determined by the vertical neighborhood, then the neighborhood of this point is (m, n-floor(L / 2): n+floor(L / 2)). As another example, when determining the data analysis region using both horizontal and vertical neighborhoods, if the current point's coordinates are (m, n), then the neighborhood of this point can be (m-floor(L / 2): m+floor(L / 2), n-floor(L / 2): n+floor(L / 2)).

[0067] It should be noted that each point in the point cloud data can be used as the center point to determine its corresponding data analysis area, and the point can be analyzed to determine whether it is an artifact point based on the data analysis area.

[0068] It should also be noted that the data analysis area for each point can be a single horizontal neighborhood (i.e., the data analysis area for that point is only the horizontal neighborhood), a single vertical neighborhood (i.e., the data analysis area for that point is only the vertical neighborhood), or a combination of horizontal and vertical neighborhoods (i.e., the data analysis area for that point includes both horizontal and vertical neighborhoods), without any restrictions.

[0069] S12: Determine the statistical results of points in the data analysis area that meet the preset statistical conditions based on the distance difference value of each point.

[0070] In this embodiment of the application, after determining the data analysis area for each point, it can be determined whether the points in the data analysis area meet the preset statistical conditions based on the distance difference value of each point contained in the data analysis area.

[0071] It should be noted that the preset statistical conditions can be set according to the actual situation. For example, the absolute value of the difference value of each point can be set to be greater than a certain threshold. If the preset statistical conditions are met, the point will be recorded in the first statistical result.

[0072] In one embodiment of this application, the following steps may be included before S12:

[0073] Calculate the distance difference value for each point in the data analysis area.

[0074] For any point in point cloud data, after determining its data analysis area, the distance difference value of each point in that data analysis area can be calculated.

[0075] The distance difference value described in the embodiments of this application refers to the difference between the distance at the next time step and the distance at the current time step. The distance difference value of each point can be expressed as formula (1).

[0076] Where Diff(i) is the distance difference of point i, Dist(i+1) is the distance of point i at the next time step, and Dist(i) is the distance of point i at the current time step.

[0077] Diff(i)=Dist(i+1)-Dist(i)(1)

[0078] Please see Figure 4 In one embodiment of this application, S12 may include S21 to S25.

[0079] S21: Weight the points in the data analysis area whose distance difference value is greater than a specific threshold and record them as the first statistical result.

[0080] In this embodiment of the application, the data analysis area is taken as a horizontal neighborhood as an example. The points whose absolute value of the distance difference result in the neighborhood of row 1 * column L is greater than a certain threshold are statistically analyzed by weighting. The statistical result is recorded as the first statistical result Cnt1. The position IndexList (record coordinate value) of the points that meet the conditions and their distance difference value DiffList are also recorded.

[0081] Specifically, the judgment condition is shown in the following formula (2), where Diff represents the difference result of each point, Dist represents the distance value of the current point, θ represents the angular resolution of the lidar, and ψ represents the angle judgment threshold, with a typical value of 0.2 rad.

[0082] |Diff|>Dis×sin(θ) / tan(ψ)(2)

[0083] It should be noted that, since the distance of the dragged point cloud changes rapidly and continuously from one distance to another, and the angular resolution is small enough, the direction vector formed by its point cloud appears to point approximately to the origin of the point cloud coordinate system. Therefore, the judgment condition is set as in formula (2).

[0084] For example, please refer to Figure 5Where A and B are artifact points formed by dragging point phenomenon. If vector BA approximately points to the center O, then ∠ABC must be small enough, let's assume it's ψ. Based on this, we can deduce the conditions that the point cloud distance data needs to satisfy. When Dist is large enough and the angular resolution θ is small enough, the distance of CO is approximately equal to AO. Then BC can be approximately considered as the distance difference Diff between points A and B. Based on trigonometric geometric relations, we can obtain formula (2).

[0085] It should be noted that the first statistical result Cnt1 is obtained by weighting the judgment result of formula (2) and the position of the current point in the horizontal neighborhood. The weight of each point in the data analysis area can be determined based on its distance from the center point. For example, the closer the point is to the center point, the greater the weight; the farther the point is from the center point, the smaller the weight.

[0086] It should also be noted that the weighting coefficients for each point can be adjusted according to the actual situation, such as the weighting coefficients following a linear decrease or a Gaussian decrease.

[0087] S22: Count the number of points with consecutive coordinates based on the coordinate positions of each point in the first statistical result, and record it as the second statistical result.

[0088] It should be noted that the above continuous coordinates refer to the coordinate numbers 1, 2, 3, 4, 5 of the points in the first statistical result, which are continuous, rather than the jumps 1, 4, 8.

[0089] Specifically, the coordinate sequence of a point can be determined based on the position IndexList of the point in S21, and then it can be determined whether the coordinates of each point are continuous. If the coordinates are continuous, the point is counted as a point with continuous coordinates and recorded in the second statistical result Cnt2.

[0090] S23: Based on the difference distance values ​​of each point in the first statistical result, count the number of points whose distance increased and the number of points whose distance decreased, and record them as the third statistical result and the fourth statistical result, respectively.

[0091] In this embodiment of the application, the number of points whose distance increases in the list is determined based on the distance difference value DiffList in S21, that is, the number of points with Diff greater than 0, and recorded as the third statistical result Cnt3; the number of points whose distance decreases in the list is determined based on the distance difference value DiffList in S21, that is, the number of points with Diff less than 0, and recorded as the fourth statistical result Cnt4.

[0092] S24: Based on the difference distance values ​​of each point in the first statistical result, count the number of points where the distance difference between two consecutive points is not equal or does not satisfy the equal ratio relationship, and record it as the fifth statistical result.

[0093] In this embodiment of the application, based on whether the distance difference between two consecutive points in the DiffList segment of the distance difference value in S21 is equal or satisfies a geometric relationship, the number of points where the distance difference between two consecutive points is not equal or does not satisfy a geometric relationship is counted and recorded as the fifth statistical result Cnt5.

[0094] It should be noted that two consecutive points refer to two points whose coordinates are adjacent.

[0095] S25: If the distance difference between the first and last points of the data analysis area is greater than the first preset threshold and less than the second preset threshold, then the variable identifier is set.

[0096] In this embodiment of the application, the first and last points of the data analysis area refer to the first and last points of the data analysis area. The first and last points of the data analysis area can be determined based on the coordinates of each point in the data analysis area, and the distance difference between the first and last points can be calculated.

[0097] It should be noted that the first preset threshold and the second preset threshold can be set according to actual applications, and this application does not impose any restrictions on them.

[0098] Setting the variable identifier Logic1 can be either set to 1 or 0. For example, when the distance difference between the first and last points of the data analysis area is greater than a first preset threshold and less than a second preset threshold, the variable identifier Logic1 is set to 1.

[0099] S13: Based on the statistical results, identify the artifact points in the point cloud data.

[0100] In this embodiment of the application, after obtaining the statistical results, it is possible to determine whether the point is an artifact point based on the statistical results. By judging the statistical results corresponding to each point in the point cloud data based on the recognition conditions, all artifact points in the point cloud data can be identified.

[0101] In one embodiment of this application, S13 may include the following steps:

[0102] Set recognition conditions based on recognition accuracy;

[0103] Based on the identification conditions, the statistical results are judged to determine the artifact points in the point cloud data.

[0104] Recognition accuracy refers to the strength of artifact removal. If it is necessary to increase the strength of artifact removal, the recognition accuracy should be set higher; if it is necessary to decrease the strength of artifact removal, the recognition accuracy should be set lower.

[0105] After determining the recognition accuracy, multiple joint recognition conditions can be set. Only when all multiple recognition conditions are met will the center point of the data analysis area be determined as the artifact point.

[0106] When setting recognition conditions, they can be based on the statistical results of S12. If the recognition accuracy is high, the recognition conditions can be set based on multiple statistical results. If the recognition accuracy is low, the recognition conditions can be set based on only one or two statistical results. In application, the settings can be made according to the actual situation. This application will not elaborate on this further.

[0107] For example, the above identification conditions may be: if the first statistical result is greater than the first statistical threshold, the second statistical result is greater than the second statistical threshold, the fifth statistical result is greater than the third statistical threshold, the variable identifier is set, and the distance difference monotonically increases or decreases, then the center point of the data analysis area is determined to be an artifact point; otherwise, the center point of the data analysis area is determined not to be an artifact point.

[0108] For example, the above identification conditions may be: if the first statistical result is greater than the first statistical threshold, the second statistical result is greater than the second statistical threshold, the fifth statistical result is greater than the third statistical threshold, the variable identifier is set, the third statistical result or the fourth statistical result is less than or equal to the fourth statistical threshold, and the point before the current point is an artifact point, then the center point of the data analysis area is determined to be an artifact point; otherwise, the center point of the data analysis area is determined not to be an artifact point.

[0109] As can be seen from the above, the artifact point recognition method provided in this application embodiment can accurately identify artifact points in the point cloud data by sliding through each point in the point cloud data, statistically analyzing the points that meet the preset statistical conditions based on the distance difference results of the point cloud, and then accurately identifying the artifact points in the point cloud data based on the statistical results.

[0110] In another embodiment of this application, the above-described artifact point identification method may further include the following steps:

[0111] Remove the artifact points from the point cloud data.

[0112] In this embodiment of the application, after identifying the artifact point, the point flag Invalid of the artifact point can be set to 1 to identify the point as an artifact point.

[0113] By removing all points with the Invalid flag set to 1 from the point cloud data, artifact points can be removed from the point cloud data.

[0114] To more intuitively demonstrate the beneficial effects of the artifact point recognition method provided in the embodiments of this application, Figure 6The diagram shows a point cloud image containing artifact points (the arrows indicate the artifact points) and a point cloud image after the artifact points have been removed using the artifact point recognition method provided in this application.

[0115] Depend on Figure 6 It is evident that the artifact point recognition method provided in this application embodiment can effectively remove artifact points in point cloud images and well preserve the point cloud of real objects, thereby effectively improving ranging accuracy.

[0116] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0117] Based on the artifact point recognition method provided in the above embodiments, the present invention further provides an embodiment of a terminal device that implements the above method embodiments.

[0118] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. In this embodiment, the terminal device includes units used for performing... Figure 3 The steps in the corresponding embodiments. Please refer to the details. Figure 3 as well as Figure 3 The relevant descriptions in the corresponding embodiments are shown below. For ease of explanation, only the parts relevant to this embodiment are shown. Figure 7 As shown, the terminal device 70 includes: a determining unit 71, a statistical unit 72, and an identification unit 73. Wherein:

[0119] The determining unit 71 is used to perform a sliding traversal of each point in the point cloud data returned by the radar to determine the data analysis area of ​​each point.

[0120] The statistical unit 72 is used to determine the statistical results of points in the data analysis area that meet the preset statistical conditions based on the distance difference value of each point.

[0121] The identification unit 73 is used to identify artifact points in the point cloud data based on the statistical results.

[0122] In one embodiment of this application, the terminal device may further include a computing unit, which is used to calculate the distance difference value of each point in the data analysis area.

[0123] In one embodiment of this application, the above-mentioned identification unit includes a condition setting unit and a judgment unit, wherein: the condition setting unit is used to set identification conditions according to the identification accuracy; the judgment unit is used to judge the statistical results based on the identification conditions to determine the artifact points in the point cloud data.

[0124] In one embodiment of this application, the statistical unit 72 is specifically used to weight and count points in the data analysis area whose distance difference value is greater than a specific threshold, and record them as a first statistical result; count the number of consecutive points based on the coordinate positions of each point in the first statistical result, and record them as a second statistical result; count the number of points whose distance increases and decreases based on the difference distance value of each point in the first statistical result, and record them as a third and fourth statistical result, respectively; count the number of points whose distance difference between two consecutive points is not equal or does not satisfy the proportional relationship based on the difference distance value of each point in the first statistical result, and record them as a fifth statistical result; if the distance difference between the first and last points in the data analysis area is greater than a first preset threshold and less than a second preset threshold, then the variable identifier is set.

[0125] It should be noted that the information interaction and execution process between the above-mentioned units are based on the same concept as the method embodiments of this application. Their specific functions and technical effects can be referred to the method embodiments section, and will not be repeated here.

[0126] Figure 8 This is a schematic diagram of the structure of a terminal device provided in another embodiment of this application. For example... Figure 8 As shown, the terminal device 8 provided in this embodiment includes: a processor 80, a memory 81, and a computer program 82 stored in the memory 81 and executable on the processor 80, such as an image segmentation program. When the processor 80 executes the computer program 82, it implements the steps in the various artifact point recognition method embodiments described above, for example... Figure 3 S11~S13 are shown. Alternatively, when the processor 80 executes the computer program 82, it implements the functions of each module / unit in the above-described terminal device embodiments, for example... Figure 7 The functions of units 71-73 shown.

[0127] For example, the computer program 82 can be divided into one or more modules / units, which are stored in the memory 81 and executed by the processor 80 to complete this application. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 82 in the terminal device 8. For example, the computer program 82 can be divided into a first acquisition unit and a first processing unit; for the specific functions of each unit, please refer to [link to relevant documentation]. Figure 5 The relevant descriptions in the corresponding embodiments are not repeated here.

[0128] The terminal device may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will understand that... Figure 8This is merely an example of terminal device 8 and does not constitute a limitation on terminal device 8. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal device may also include input / output devices, network access devices, buses, etc.

[0129] The processor 80 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0130] The memory 81 can be an internal storage unit of the terminal device 8, such as a hard disk or memory of the terminal device 8. The memory 81 can also be an external storage device of the terminal device 8, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal device 8. Furthermore, the memory 81 can include both internal and external storage units of the terminal device 8. The memory 81 is used to store the computer program and other programs and data required by the terminal device. The memory 81 can also be used to temporarily store data that has been output or will be output.

[0131] This application also provides a computer-readable storage medium. Please refer to... Figure 9 , Figure 9 This is a schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of this application, such as... Figure 9 As shown, a computer-readable storage medium 90 stores a computer program 91, which, when executed by a processor, can implement the aforementioned artifact point recognition method.

[0132] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the aforementioned artifact point recognition method.

[0133] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the terminal device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0134] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.

[0135] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0136] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for artifact point identification, characterized in that, include: A sliding traversal is performed on each point in the point cloud data transmitted back by the radar to determine the data analysis area for each point; Calculate the distance difference value for each point in the data analysis area; The statistical results of points in the data analysis area that meet the preset statistical conditions are determined based on the distance difference value of each point; Based on the statistical results, artifact points in the point cloud data are identified; The step of determining the statistical results of points in the data analysis area that meet preset statistical conditions based on the distance difference value of each point includes: Points in the data analysis area with a distance difference greater than a specific threshold are weighted and recorded as the first statistical result; The number of consecutive points based on the coordinates of each point in the first statistical result is counted and recorded as the second statistical result; Based on the difference distance values ​​of each point in the first statistical result, count the number of points whose distance increased and the number of points whose distance decreased, and record them as the third statistical result and the fourth statistical result, respectively. Based on the difference distance values ​​of each point in the first statistical result, count the number of points where the distance difference between two consecutive points is not equal or does not satisfy the geometric relationship, and record it as the fifth statistical result; If the distance difference between the first and last points of the data analysis area is greater than the first preset threshold and less than the second preset threshold, then the variable identifier will be set.

2. The artifact point recognition method according to claim 1, characterized in that, The process of identifying artifact points in the point cloud data based on the statistical results includes: Set recognition conditions based on recognition accuracy; Based on the identification conditions, the statistical results are judged to determine the artifact points in the point cloud data.

3. The artifact point recognition method according to claim 1, characterized in that, If the first statistical result is greater than the first statistical threshold, the second statistical result is greater than the second statistical threshold, the fifth statistical result is greater than the third statistical threshold, the variable identifier is set, and the distance difference monotonically increases or decreases, then the center point of the data analysis area is determined to be the artifact point.

4. The artifact point recognition method according to claim 1, characterized in that, If the first statistical result is greater than the first statistical threshold, the second statistical result is greater than the second statistical threshold, the fifth statistical result is greater than the third statistical threshold, the variable identifier is set, the third statistical result or the fourth statistical result is less than or equal to the fourth statistical threshold, and the point before the current point is an artifact point, then the center point of the data analysis area is determined to be an artifact point.

5. The artifact point recognition method according to any one of claims 1 to 4, characterized in that, Also includes: Remove the artifact points from the point cloud data.

6. A terminal device, characterized in that, include: The determination unit is used to perform a sliding traversal of each point in the point cloud data returned by the radar to determine the data analysis area of ​​each point; The calculation unit is used to calculate the distance difference value of each point in the data analysis area; The statistical unit is used to determine the statistical results of points in the data analysis area that meet preset statistical conditions based on the distance difference value of each point; The identification unit is used to identify artifact points in the point cloud data based on the statistical results; The step of determining the statistical results of points in the data analysis area that meet preset statistical conditions based on the distance difference value of each point includes: Points in the data analysis area with a distance difference greater than a specific threshold are weighted and recorded as the first statistical result; The number of consecutive points based on the coordinates of each point in the first statistical result is counted and recorded as the second statistical result; Based on the difference distance values ​​of each point in the first statistical result, count the number of points whose distance increased and the number of points whose distance decreased, and record them as the third statistical result and the fourth statistical result, respectively. Based on the difference distance values ​​of each point in the first statistical result, count the number of points where the distance difference between two consecutive points is not equal or does not satisfy the geometric relationship, and record it as the fifth statistical result; If the distance difference between the first and last points of the data analysis area is greater than the first preset threshold and less than the second preset threshold, then the variable identifier will be set.

7. The terminal device as described in claim 6, characterized in that, The identification unit includes: A condition setting unit is used to set recognition conditions based on recognition accuracy. The judgment unit is used to judge the statistical results based on the recognition conditions and determine the artifact points in the point cloud data.

8. A terminal device, comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, characterized in that, When the processor executes computer-readable instructions, it performs the following steps: A sliding traversal is performed on each point in the point cloud data transmitted back by the radar to determine the data analysis area for each point; Calculate the distance difference value for each point in the data analysis area; The statistical results of points in the data analysis area that meet the preset statistical conditions are determined based on the distance difference value of each point; Based on the statistical results, artifact points in the point cloud data are identified; The step of determining the statistical results of points in the data analysis area that meet preset statistical conditions based on the distance difference value of each point includes: Points in the data analysis area with a distance difference greater than a specific threshold are weighted and recorded as the first statistical result; The number of consecutive points based on the coordinates of each point in the first statistical result is counted and recorded as the second statistical result; Based on the difference distance values ​​of each point in the first statistical result, count the number of points whose distance increased and the number of points whose distance decreased, and record them as the third statistical result and the fourth statistical result, respectively. Based on the difference distance values ​​of each point in the first statistical result, count the number of points where the distance difference between two consecutive points is not equal or does not satisfy the geometric relationship, and record it as the fifth statistical result; If the distance difference between the first and last points of the data analysis area is greater than the first preset threshold and less than the second preset threshold, then the variable identifier will be set.

9. The terminal device as described in claim 8, characterized in that, The process of identifying artifact points in the point cloud data based on the statistical results includes: Set recognition conditions based on recognition accuracy; Based on the identification conditions, the statistical results are judged to determine the artifact points in the point cloud data.

10. The terminal device as described in any one of claims 8 to 9, characterized in that, When the processor executes the computer-readable instructions, it also performs the following steps: Remove the artifact points from the point cloud data.

11. A computer-readable storage medium storing computer-readable instructions, characterized in that, When a computer-readable instruction is executed by a processor, it performs the following steps: A sliding traversal is performed on each point in the point cloud data transmitted back by the radar to determine the data analysis area for each point; Calculate the distance difference value for each point in the data analysis area; The statistical results of points in the data analysis area that meet the preset statistical conditions are determined based on the distance difference value of each point; Based on the statistical results, artifact points in the point cloud data are identified; The step of determining the statistical results of points in the data analysis area that meet preset statistical conditions based on the distance difference value of each point includes: Points in the data analysis area with a distance difference greater than a specific threshold are weighted and recorded as the first statistical result; The number of consecutive points based on the coordinates of each point in the first statistical result is counted and recorded as the second statistical result; Based on the difference distance values ​​of each point in the first statistical result, count the number of points whose distance increased and the number of points whose distance decreased, and record them as the third statistical result and the fourth statistical result, respectively. Based on the difference distance values ​​of each point in the first statistical result, count the number of points where the distance difference between two consecutive points is not equal or does not satisfy the geometric relationship, and record it as the fifth statistical result; If the distance difference between the first and last points of the data analysis area is greater than the first preset threshold and less than the second preset threshold, then the variable identifier will be set.

12. The computer-readable storage medium as claimed in claim 11, characterized in that, The process of identifying artifact points in the point cloud data based on the statistical results includes: Set recognition conditions based on recognition accuracy; Based on the identification conditions, the statistical results are judged to determine the artifact points in the point cloud data.

13. The computer-readable storage medium as claimed in any one of claims 11 to 12, characterized in that, When the computer-readable instructions are executed by the processor, the following steps are also performed: Remove the artifact points from the point cloud data.

Images